LLM EXPLORER
 LLM Explorer: A Curated Large Language Model Directory and Analytics
Dark Theme
  Agents   Benchmarks   LLM  List    LLM Hosting    LLM Leaderboards    Blog    Newsfeed    Advertise

Hymba 1.5B Base by nvidia

 »  All LLMs  »  nvidia  »  Hymba 1.5B Base   URL Share it on

  576   

Hymba 1.5B Base is an open-source language model by nvidia. Features: 1.5b LLM, VRAM: 3GB, Context: 8K, License: other, LLM Explorer Score: 0.21.

  Arxiv:2411.13676   Autotrain compatible   Conversational   Custom code   Hymba   Region:us   Safetensors
Model Card on HF 🤗: https://huggingface.co/nvidia/Hymba-1.5B-Base 

Hymba 1.5B Base Benchmarks

MMLU Pro: 10.25
GPQA: 0.78
MUSR: 5.18
BBH: 7.69
IFEval: 22.95 vs 88 (so35)-73.9%
MATH Lvl 5: 1.36
LLME Score: 0.20698
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Hymba 1.5B Base (nvidia/Hymba-1.5B-Base)
🌟 Advertise your project 🚀

Hymba 1.5B Base Parameters and Internals

Model Type 
text-to-text
Use Cases 
Limitations:
The model may amplify biases and return toxic responses., The model may generate inaccurate or socially undesirable text., The model is susceptible to jailbreak attacks.
Additional Notes 
Meta tokens, a set of learnable tokens, are prepended to every prompt to improve efficacy. The model shares KV cache between 2 layers and between heads in a single layer. 90% of attention layers are sliding window attention.
Training Details 
Training Time:
September 1, 2024 - November 10, 2024
Model Architecture:
Hymba-1.5B-Base has a model embedding size of 1600, 25 attention heads, and an MLP intermediate dimension of 5504, with 32 layers in total, 16 SSM states, 3 full attention layers, the rest are sliding window attention. Each attention layer in Hymba has a hybrid combination of standard attention heads and Mamba heads in parallel. Additionally, it uses Grouped-Query Attention (GQA) and Rotary Position Embeddings (RoPE).
Responsible Ai Considerations 
Accountability:
Developers should work with their internal model team to ensure this model meets requirements for the relevant industry and use case and addresses unforeseen product misuse.
Mitigation Strategies:
Strong output validation controls are recommended to handle security and safety risks.
Input Output 
Performance Tips:
The batch size needs to be 1 during generation due to current implementation limitations.
LLM NameHymba 1.5B Base
Repository 🤗https://huggingface.co/nvidia/Hymba-1.5B-Base 
Model Size1.5b
Required VRAM3 GB
Updated2025-09-23
Maintainernvidia
Model Typehymba
Model Files  3.0 GB
Model ArchitectureHymbaForCausalLM
Licenseother
Context Length8192
Model Max Length8192
Transformers Version4.44.0
Tokenizer ClassLlamaTokenizer
Padding Token[PAD]
Vocabulary Size32001
Torch Data Typebfloat16

Best Alternatives to Hymba 1.5B Base

Best Alternatives
Context / RAM
Downloads
Likes
Hymba 1.5B Instruct8K / 3 GB567245
Note: green Score (e.g. "73.2") means that the model is better than nvidia/Hymba-1.5B-Base.

Rank the Hymba 1.5B Base Capabilities

🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟

Instruction Following and Task Automation  
Factuality and Completeness of Knowledge  
Censorship and Alignment  
Data Analysis and Insight Generation  
Text Generation  
Text Summarization and Feature Extraction  
Code Generation  
Multi-Language Support and Translation  

What open-source LLMs or SLMs are you in search of? 52721 in total.

Email us: info@extractum.io. Our Privacy Policy  | Terms and Conditions  | Suggest an improvement.
Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a
  Support LLM Explorer